Return to the
comp.compilers page.
Search the
comp.compilers archives again.
| Related articles |
|---|
| Figuring out grammars from examples johnl@taugh.com (John R Levine) (2024-04-12) |
| Re: Figuring out grammars from examples derek@shape-of-code.com (Derek) (2024-04-13) |
| Re: Figuring out grammars from examples derek@shape-of-code.com (Derek) (2024-04-15) |
| From: | Derek <derek@shape-of-code.com> |
| Newsgroups: | comp.compilers |
| Date: | Mon, 15 Apr 2024 02:17:04 +0100 |
| Organization: | Compilers Central |
| References: | 24-04-001 24-04-002 |
| Injection-Info: | gal.iecc.com; posting-host="news.iecc.com:2001:470:1f07:1126:0:676f:7373:6970"; logging-data="10024"; mail-complaints-to="abuse@iecc.com" |
| Keywords: | parse |
| Posted-Date: | 14 Apr 2024 22:16:37 EDT |
| In-Reply-To: | 24-04-002 |
John,
> [I would like to see some actual data. In my experience, LLMs are
> impressive, confident, and frequently wrong. -John]
LLM's performance on fact recall is poor.
It seems to be much better than other tools when dealing with
grammars. I could not find the example I was looking for, but here are
two others: https://arxiv.org/abs/2305.19234
https://szopa.medium.com/teaching-chatgpt-to-speak-my-sons-invented-language-9d109c0a0f05
My own experience using local (i.e., very small)
models
https://shape-of-code.com/2024/02/25/extracting-named-entities-from-a-change-log-using-an-llm/
Return to the
comp.compilers page.
Search the
comp.compilers archives again.